You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by pw...@apache.org on 2014/04/10 08:26:37 UTC
[2/3] git commit: [SPARK-1357 (fix)] remove empty line after ::
DeveloperApi/Experimental ::
[SPARK-1357 (fix)] remove empty line after :: DeveloperApi/Experimental ::
Remove empty line after :: DeveloperApi/Experimental :: in comments to make the original doc show up in the preview of the generated html docs. Thanks @andrewor14 !
Author: Xiangrui Meng <me...@databricks.com>
Closes #373 from mengxr/api and squashes the following commits:
9c35bdc [Xiangrui Meng] remove the empty line after :: DeveloperApi/Experimental ::
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/0adc932a
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/0adc932a
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/0adc932a
Branch: refs/heads/branch-1.0
Commit: 0adc932add413a1754107b21d5ecfb38c0c3a4eb
Parents: eb5f2b6
Author: Xiangrui Meng <me...@databricks.com>
Authored: Wed Apr 9 17:08:17 2014 -0700
Committer: Patrick Wendell <pw...@gmail.com>
Committed: Wed Apr 9 17:08:17 2014 -0700
----------------------------------------------------------------------
.../spark/mllib/api/python/PythonMLLibAPI.scala | 1 -
.../spark/mllib/classification/NaiveBayes.scala | 1 -
.../apache/spark/mllib/clustering/KMeans.scala | 4 --
.../linalg/distributed/CoordinateMatrix.scala | 1 -
.../linalg/distributed/IndexedRowMatrix.scala | 2 -
.../mllib/linalg/distributed/RowMatrix.scala | 1 -
.../spark/mllib/optimization/Gradient.scala | 4 --
.../mllib/optimization/GradientDescent.scala | 2 -
.../spark/mllib/optimization/Optimizer.scala | 1 -
.../spark/mllib/optimization/Updater.scala | 4 --
.../apache/spark/mllib/recommendation/ALS.scala | 1 -
.../MatrixFactorizationModel.scala | 1 -
.../regression/GeneralizedLinearAlgorithm.scala | 1 -
.../apache/spark/mllib/tree/DecisionTree.scala | 1 -
.../spark/mllib/tree/configuration/Algo.scala | 1 -
.../mllib/tree/configuration/FeatureType.scala | 1 -
.../tree/configuration/QuantileStrategy.scala | 1 -
.../mllib/tree/configuration/Strategy.scala | 1 -
.../spark/mllib/tree/impurity/Entropy.scala | 2 -
.../apache/spark/mllib/tree/impurity/Gini.scala | 2 -
.../spark/mllib/tree/impurity/Impurity.scala | 3 --
.../spark/mllib/tree/impurity/Variance.scala | 2 -
.../mllib/tree/model/DecisionTreeModel.scala | 1 -
.../mllib/tree/model/InformationGainStats.scala | 1 -
.../apache/spark/mllib/tree/model/Node.scala | 1 -
.../apache/spark/mllib/tree/model/Split.scala | 1 -
.../spark/mllib/util/DataValidators.scala | 1 -
.../spark/mllib/util/KMeansDataGenerator.scala | 1 -
.../spark/mllib/util/LinearDataGenerator.scala | 1 -
.../util/LogisticRegressionDataGenerator.scala | 1 -
.../spark/mllib/util/MFDataGenerator.scala | 43 ++++++++++----------
.../org/apache/spark/mllib/util/MLUtils.scala | 2 -
.../spark/mllib/util/SVMDataGenerator.scala | 1 -
33 files changed, 21 insertions(+), 71 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala b/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
index ae27c57..a6c049e 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
@@ -30,7 +30,6 @@ import org.apache.spark.rdd.RDD
/**
* :: DeveloperApi ::
- *
* The Java stubs necessary for the Python mllib bindings.
*/
@DeveloperApi
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala b/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala
index 5a45f12..1865885 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala
@@ -29,7 +29,6 @@ import org.apache.spark.rdd.RDD
/**
* :: Experimental ::
- *
* Model for Naive Bayes Classifiers.
*
* @param labels list of labels
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala
index 8f565eb..90cf852 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala
@@ -78,7 +78,6 @@ class KMeans private (
/**
* :: Experimental ::
- *
* Set the number of runs of the algorithm to execute in parallel. We initialize the algorithm
* this many times with random starting conditions (configured by the initialization mode), then
* return the best clustering found over any run. Default: 1.
@@ -398,9 +397,6 @@ object KMeans {
MLUtils.fastSquaredDistance(v1.vector, v1.norm, v2.vector, v2.norm)
}
- /**
- * :: Experimental ::
- */
@Experimental
def main(args: Array[String]) {
if (args.length < 4) {
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/CoordinateMatrix.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/CoordinateMatrix.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/CoordinateMatrix.scala
index 89d5c03..56b8fdc 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/CoordinateMatrix.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/CoordinateMatrix.scala
@@ -34,7 +34,6 @@ case class MatrixEntry(i: Long, j: Long, value: Double)
/**
* :: Experimental ::
- *
* Represents a matrix in coordinate format.
*
* @param entries matrix entries
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala
index 24c123a..132b3af 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala
@@ -26,7 +26,6 @@ import org.apache.spark.mllib.linalg.SingularValueDecomposition
/**
* :: Experimental ::
- *
* Represents a row of [[org.apache.spark.mllib.linalg.distributed.IndexedRowMatrix]].
*/
@Experimental
@@ -34,7 +33,6 @@ case class IndexedRow(index: Long, vector: Vector)
/**
* :: Experimental ::
- *
* Represents a row-oriented [[org.apache.spark.mllib.linalg.distributed.DistributedMatrix]] with
* indexed rows.
*
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala
index 8d32c1a..f65f43d 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala
@@ -30,7 +30,6 @@ import org.apache.spark.Logging
/**
* :: Experimental ::
- *
* Represents a row-oriented distributed Matrix with no meaningful row indices.
*
* @param rows rows stored as an RDD[Vector]
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala b/mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala
index 1176dc9..679842f 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala
@@ -24,7 +24,6 @@ import org.apache.spark.mllib.linalg.{Vectors, Vector}
/**
* :: DeveloperApi ::
- *
* Class used to compute the gradient for a loss function, given a single data point.
*/
@DeveloperApi
@@ -56,7 +55,6 @@ abstract class Gradient extends Serializable {
/**
* :: DeveloperApi ::
- *
* Compute gradient and loss for a logistic loss function, as used in binary classification.
* See also the documentation for the precise formulation.
*/
@@ -100,7 +98,6 @@ class LogisticGradient extends Gradient {
/**
* :: DeveloperApi ::
- *
* Compute gradient and loss for a Least-squared loss function, as used in linear regression.
* This is correct for the averaged least squares loss function (mean squared error)
* L = 1/n ||A weights-y||^2
@@ -135,7 +132,6 @@ class LeastSquaresGradient extends Gradient {
/**
* :: DeveloperApi ::
- *
* Compute gradient and loss for a Hinge loss function, as used in SVM binary classification.
* See also the documentation for the precise formulation.
* NOTE: This assumes that the labels are {0,1}
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/optimization/GradientDescent.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/optimization/GradientDescent.scala b/mllib/src/main/scala/org/apache/spark/mllib/optimization/GradientDescent.scala
index 04267d9..f60417f 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/optimization/GradientDescent.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/optimization/GradientDescent.scala
@@ -28,7 +28,6 @@ import org.apache.spark.mllib.linalg.{Vectors, Vector}
/**
* :: DeveloperApi ::
- *
* Class used to solve an optimization problem using Gradient Descent.
* @param gradient Gradient function to be used.
* @param updater Updater to be used to update weights after every iteration.
@@ -113,7 +112,6 @@ class GradientDescent(private var gradient: Gradient, private var updater: Updat
/**
* :: DeveloperApi ::
- *
* Top-level method to run gradient descent.
*/
@DeveloperApi
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/optimization/Optimizer.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/optimization/Optimizer.scala b/mllib/src/main/scala/org/apache/spark/mllib/optimization/Optimizer.scala
index 0a313f3..e41d9bb 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/optimization/Optimizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/optimization/Optimizer.scala
@@ -24,7 +24,6 @@ import org.apache.spark.mllib.linalg.Vector
/**
* :: DeveloperApi ::
- *
* Trait for optimization problem solvers.
*/
@DeveloperApi
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/optimization/Updater.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/optimization/Updater.scala b/mllib/src/main/scala/org/apache/spark/mllib/optimization/Updater.scala
index e678167..3ed3a5b 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/optimization/Updater.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/optimization/Updater.scala
@@ -26,7 +26,6 @@ import org.apache.spark.mllib.linalg.{Vectors, Vector}
/**
* :: DeveloperApi ::
- *
* Class used to perform steps (weight update) using Gradient Descent methods.
*
* For general minimization problems, or for regularized problems of the form
@@ -64,7 +63,6 @@ abstract class Updater extends Serializable {
/**
* :: DeveloperApi ::
- *
* A simple updater for gradient descent *without* any regularization.
* Uses a step-size decreasing with the square root of the number of iterations.
*/
@@ -86,7 +84,6 @@ class SimpleUpdater extends Updater {
/**
* :: DeveloperApi ::
- *
* Updater for L1 regularized problems.
* R(w) = ||w||_1
* Uses a step-size decreasing with the square root of the number of iterations.
@@ -131,7 +128,6 @@ class L1Updater extends Updater {
/**
* :: DeveloperApi ::
- *
* Updater for L2 regularized problems.
* R(w) = 1/2 ||w||^2
* Uses a step-size decreasing with the square root of the number of iterations.
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala b/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala
index 60cbb1c..5cc47de 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala
@@ -140,7 +140,6 @@ class ALS private (
/**
* :: Experimental ::
- *
* Sets the constant used in computing confidence in implicit ALS. Default: 1.0.
*/
@Experimental
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala b/mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala
index e05224f..471546c 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala
@@ -70,7 +70,6 @@ class MatrixFactorizationModel(
/**
* :: DeveloperApi ::
- *
* Predict the rating of many users for many products.
* This is a Java stub for python predictAll()
*
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/regression/GeneralizedLinearAlgorithm.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/GeneralizedLinearAlgorithm.scala b/mllib/src/main/scala/org/apache/spark/mllib/regression/GeneralizedLinearAlgorithm.scala
index c24f5af..3bd0017 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/regression/GeneralizedLinearAlgorithm.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/regression/GeneralizedLinearAlgorithm.scala
@@ -103,7 +103,6 @@ abstract class GeneralizedLinearAlgorithm[M <: GeneralizedLinearModel]
/**
* :: Experimental ::
- *
* Set if the algorithm should validate data before training. Default true.
*/
@Experimental
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala
index c8a966c..3019447 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala
@@ -35,7 +35,6 @@ import org.apache.spark.mllib.linalg.{Vector, Vectors}
/**
* :: Experimental ::
- *
* A class that implements a decision tree algorithm for classification and regression. It
* supports both continuous and categorical features.
* @param strategy The configuration parameters for the tree algorithm which specify the type
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Algo.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Algo.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Algo.scala
index 017f84f..79a01f5 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Algo.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Algo.scala
@@ -21,7 +21,6 @@ import org.apache.spark.annotation.Experimental
/**
* :: Experimental ::
- *
* Enum to select the algorithm for the decision tree
*/
@Experimental
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/FeatureType.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/FeatureType.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/FeatureType.scala
index c0254c3..f4c8772 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/FeatureType.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/FeatureType.scala
@@ -21,7 +21,6 @@ import org.apache.spark.annotation.Experimental
/**
* :: Experimental ::
- *
* Enum to describe whether a feature is "continuous" or "categorical"
*/
@Experimental
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/QuantileStrategy.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/QuantileStrategy.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/QuantileStrategy.scala
index b3e8b22..7da976e 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/QuantileStrategy.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/QuantileStrategy.scala
@@ -21,7 +21,6 @@ import org.apache.spark.annotation.Experimental
/**
* :: Experimental ::
- *
* Enum for selecting the quantile calculation strategy
*/
@Experimental
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala
index 482faaa..8767aca 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala
@@ -24,7 +24,6 @@ import org.apache.spark.mllib.tree.configuration.QuantileStrategy._
/**
* :: Experimental ::
- *
* Stores all the configuration options for tree construction
* @param algo classification or regression
* @param impurity criterion used for information gain calculation
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Entropy.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Entropy.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Entropy.scala
index 55c43f2..60f43e9 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Entropy.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Entropy.scala
@@ -21,7 +21,6 @@ import org.apache.spark.annotation.{DeveloperApi, Experimental}
/**
* :: Experimental ::
- *
* Class for calculating [[http://en.wikipedia.org/wiki/Binary_entropy_function entropy]] during
* binary classification.
*/
@@ -32,7 +31,6 @@ object Entropy extends Impurity {
/**
* :: DeveloperApi ::
- *
* entropy calculation
* @param c0 count of instances with label 0
* @param c1 count of instances with label 1
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala
index c923b8e..c51d76d 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala
@@ -21,7 +21,6 @@ import org.apache.spark.annotation.{DeveloperApi, Experimental}
/**
* :: Experimental ::
- *
* Class for calculating the
* [[http://en.wikipedia.org/wiki/Decision_tree_learning#Gini_impurity Gini impurity]]
* during binary classification.
@@ -31,7 +30,6 @@ object Gini extends Impurity {
/**
* :: DeveloperApi ::
- *
* Gini coefficient calculation
* @param c0 count of instances with label 0
* @param c1 count of instances with label 1
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala
index f407796..8eab247 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala
@@ -21,7 +21,6 @@ import org.apache.spark.annotation.{DeveloperApi, Experimental}
/**
* :: Experimental ::
- *
* Trait for calculating information gain.
*/
@Experimental
@@ -29,7 +28,6 @@ trait Impurity extends Serializable {
/**
* :: DeveloperApi ::
- *
* information calculation for binary classification
* @param c0 count of instances with label 0
* @param c1 count of instances with label 1
@@ -40,7 +38,6 @@ trait Impurity extends Serializable {
/**
* :: DeveloperApi ::
- *
* information calculation for regression
* @param count number of instances
* @param sum sum of labels
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Variance.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Variance.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Variance.scala
index 2c64644..47d0712 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Variance.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Variance.scala
@@ -21,7 +21,6 @@ import org.apache.spark.annotation.{DeveloperApi, Experimental}
/**
* :: Experimental ::
- *
* Class for calculating variance during regression
*/
@Experimental
@@ -31,7 +30,6 @@ object Variance extends Impurity {
/**
* :: DeveloperApi ::
- *
* variance calculation
* @param count number of instances
* @param sum sum of labels
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala
index 0f76f4a..bf692ca 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala
@@ -24,7 +24,6 @@ import org.apache.spark.mllib.linalg.Vector
/**
* :: Experimental ::
- *
* Model to store the decision tree parameters
* @param topNode root node
* @param algo algorithm type -- classification or regression
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/InformationGainStats.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/InformationGainStats.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/InformationGainStats.scala
index d36b58e..cc8a24c 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/InformationGainStats.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/InformationGainStats.scala
@@ -21,7 +21,6 @@ import org.apache.spark.annotation.DeveloperApi
/**
* :: DeveloperApi ::
- *
* Information gain statistics for each split
* @param gain information gain value
* @param impurity current node impurity
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala
index 3399721..682f213 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala
@@ -24,7 +24,6 @@ import org.apache.spark.mllib.linalg.Vector
/**
* :: DeveloperApi ::
- *
* Node in a decision tree
* @param id integer node id
* @param predict predicted value at the node
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Split.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Split.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Split.scala
index 8bbb343..d7ffd38 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Split.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Split.scala
@@ -22,7 +22,6 @@ import org.apache.spark.mllib.tree.configuration.FeatureType.FeatureType
/**
* :: DeveloperApi ::
- *
* Split applied to a feature
* @param feature feature index
* @param threshold threshold for continuous feature
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/util/DataValidators.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/DataValidators.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/DataValidators.scala
index 230c409..45f9548 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/util/DataValidators.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/util/DataValidators.scala
@@ -24,7 +24,6 @@ import org.apache.spark.mllib.regression.LabeledPoint
/**
* :: DeveloperApi ::
- *
* A collection of methods used to validate data before applying ML algorithms.
*/
@DeveloperApi
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/util/KMeansDataGenerator.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/KMeansDataGenerator.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/KMeansDataGenerator.scala
index e693d13..6eaebaf 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/util/KMeansDataGenerator.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/util/KMeansDataGenerator.scala
@@ -25,7 +25,6 @@ import org.apache.spark.rdd.RDD
/**
* :: DeveloperApi ::
- *
* Generate test data for KMeans. This class first chooses k cluster centers
* from a d-dimensional Gaussian distribution scaled by factor r and then creates a Gaussian
* cluster with scale 1 around each center.
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala
index 140ff92..c8e160d 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala
@@ -30,7 +30,6 @@ import org.apache.spark.mllib.regression.LabeledPoint
/**
* :: DeveloperApi ::
- *
* Generate sample data used for Linear Data. This class generates
* uniformly random values for every feature and adds Gaussian noise with mean `eps` to the
* response variable `Y`.
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/util/LogisticRegressionDataGenerator.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/LogisticRegressionDataGenerator.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/LogisticRegressionDataGenerator.scala
index ca06b9a..c82cd8f 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/util/LogisticRegressionDataGenerator.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/util/LogisticRegressionDataGenerator.scala
@@ -27,7 +27,6 @@ import org.apache.spark.mllib.linalg.Vectors
/**
* :: DeveloperApi ::
- *
* Generate test data for LogisticRegression. This class chooses positive labels
* with probability `probOne` and scales features for positive examples by `eps`.
*/
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/util/MFDataGenerator.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/MFDataGenerator.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/MFDataGenerator.scala
index 3bd86d6..3f413fa 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/util/MFDataGenerator.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/util/MFDataGenerator.scala
@@ -27,29 +27,28 @@ import org.apache.spark.rdd.RDD
/**
* :: DeveloperApi ::
+ * Generate RDD(s) containing data for Matrix Factorization.
*
-* Generate RDD(s) containing data for Matrix Factorization.
-*
-* This method samples training entries according to the oversampling factor
-* 'trainSampFact', which is a multiplicative factor of the number of
-* degrees of freedom of the matrix: rank*(m+n-rank).
-*
-* It optionally samples entries for a testing matrix using
-* 'testSampFact', the percentage of the number of training entries
-* to use for testing.
-*
-* This method takes the following inputs:
-* sparkMaster (String) The master URL.
-* outputPath (String) Directory to save output.
-* m (Int) Number of rows in data matrix.
-* n (Int) Number of columns in data matrix.
-* rank (Int) Underlying rank of data matrix.
-* trainSampFact (Double) Oversampling factor.
-* noise (Boolean) Whether to add gaussian noise to training data.
-* sigma (Double) Standard deviation of added gaussian noise.
-* test (Boolean) Whether to create testing RDD.
-* testSampFact (Double) Percentage of training data to use as test data.
-*/
+ * This method samples training entries according to the oversampling factor
+ * 'trainSampFact', which is a multiplicative factor of the number of
+ * degrees of freedom of the matrix: rank*(m+n-rank).
+ *
+ * It optionally samples entries for a testing matrix using
+ * 'testSampFact', the percentage of the number of training entries
+ * to use for testing.
+ *
+ * This method takes the following inputs:
+ * sparkMaster (String) The master URL.
+ * outputPath (String) Directory to save output.
+ * m (Int) Number of rows in data matrix.
+ * n (Int) Number of columns in data matrix.
+ * rank (Int) Underlying rank of data matrix.
+ * trainSampFact (Double) Oversampling factor.
+ * noise (Boolean) Whether to add gaussian noise to training data.
+ * sigma (Double) Standard deviation of added gaussian noise.
+ * test (Boolean) Whether to create testing RDD.
+ * testSampFact (Double) Percentage of training data to use as test data.
+ */
@DeveloperApi
object MFDataGenerator {
def main(args: Array[String]) {
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala
index 7f9804d..ac2360c 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala
@@ -124,7 +124,6 @@ object MLUtils {
/**
* :: Experimental ::
- *
* Load labeled data from a file. The data format used here is
* <L>, <f1> <f2> ...
* where <f1>, <f2> are feature values in Double and <L> is the corresponding label as Double.
@@ -146,7 +145,6 @@ object MLUtils {
/**
* :: Experimental ::
- *
* Save labeled data to a file. The data format used here is
* <L>, <f1> <f2> ...
* where <f1>, <f2> are feature values in Double and <L> is the corresponding label as Double.
http://git-wip-us.apache.org/repos/asf/spark/blob/0adc932a/mllib/src/main/scala/org/apache/spark/mllib/util/SVMDataGenerator.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/SVMDataGenerator.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/SVMDataGenerator.scala
index 87a6f2a..ba8190b 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/util/SVMDataGenerator.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/util/SVMDataGenerator.scala
@@ -29,7 +29,6 @@ import org.apache.spark.mllib.regression.LabeledPoint
/**
* :: DeveloperApi ::
- *
* Generate sample data used for SVM. This class generates uniform random values
* for the features and adds Gaussian noise with weight 0.1 to generate labels.
*/